Qwen3-Coder-30B-A3B-Instruct

Open weights Active Text LLM MoE qwen3-coder-30b-a3b

Small MoE agentic coding model distilled from the Qwen3-Coder line.

Released
Jul 31, 2025
Context window
262K tokens
Max output
Not disclosed
Parameters
30.5B 3.3B active
Input price
Not disclosed
Output price
Not disclosed

Prices are first-party list prices in USD at the standard tier. Last verified Oct 30, 2026.

Pricing

No first-party API. This is an open-weights release you can run yourself.

Specifications

Developer
Alibaba
Model type
Text LLM
Architecture
MoE
Parameters
30.5B (3.3B active)
Input
Text
Output
Text
Knowledge cutoff
Not disclosed
License
Apache License 2.0
API access
No first-party API
Capabilities
Agentic Coding Long context